Demografia w Polsce i Europie

Dane z Eurostatu (11/07/2022): https://ec.europa.eu/eurostat/web/population-demography/demography-population-stock-balance/database

import numpy as np
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go
import plotly.io as pio

Wczytanie danych

population_density = pd.read_csv('F:\\STUDIA\\7SEM\\mit\\zad2\\dane\\population_density.csv')
population_density.head()

	DATAFLOW	LAST UPDATE	freq	unit	geo	TIME_PERIOD	OBS_VALUE	OBS_FLAG
0	ESTAT:TPS00003(1.0)	20/08/21 23:00:00	A	PER_KM2	AL	2012	100.7	NaN
1	ESTAT:TPS00003(1.0)	20/08/21 23:00:00	A	PER_KM2	AL	2013	100.6	NaN
2	ESTAT:TPS00003(1.0)	20/08/21 23:00:00	A	PER_KM2	AL	2014	100.4	NaN
3	ESTAT:TPS00003(1.0)	20/08/21 23:00:00	A	PER_KM2	AL	2015	100.1	NaN
4	ESTAT:TPS00003(1.0)	20/08/21 23:00:00	A	PER_KM2	AL	2016	99.9	NaN

population_density = population_density.drop(columns = ['DATAFLOW','LAST UPDATE', 'freq', 'unit', 'OBS_FLAG'])
population_density.head()

	geo	TIME_PERIOD	OBS_VALUE
0	AL	2012	100.7
1	AL	2013	100.6
2	AL	2014	100.4
3	AL	2015	100.1
4	AL	2016	99.9

population_density.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 464 entries, 0 to 463
Data columns (total 3 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   geo          464 non-null    object 
 1   TIME_PERIOD  464 non-null    int64  
 2   OBS_VALUE    464 non-null    float64
dtypes: float64(1), int64(1), object(1)
memory usage: 11.0+ KB

women_per_100_men = pd.read_csv('F:\\STUDIA\\7SEM\\mit\\zad2\\dane\\women_per_100_men.csv')
women_per_100_men.head()

	DATAFLOW	LAST UPDATE	freq	indic_de	geo	TIME_PERIOD	OBS_VALUE	OBS_FLAG
0	ESTAT:TPS00011(1.0)	22/06/22 23:00:00	A	PC_FM	AD	2010	92.0	NaN
1	ESTAT:TPS00011(1.0)	22/06/22 23:00:00	A	PC_FM	AD	2011	96.0	NaN
2	ESTAT:TPS00011(1.0)	22/06/22 23:00:00	A	PC_FM	AD	2012	96.0	NaN
3	ESTAT:TPS00011(1.0)	22/06/22 23:00:00	A	PC_FM	AD	2013	96.3	NaN
4	ESTAT:TPS00011(1.0)	22/06/22 23:00:00	A	PC_FM	AD	2019	96.4	NaN

women_per_100_men.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 593 entries, 0 to 592
Data columns (total 8 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   DATAFLOW     593 non-null    object 
 1   LAST UPDATE  593 non-null    object 
 2   freq         593 non-null    object 
 3   indic_de     593 non-null    object 
 4   geo          593 non-null    object 
 5   TIME_PERIOD  593 non-null    int64  
 6   OBS_VALUE    592 non-null    float64
 7   OBS_FLAG     66 non-null     object 
dtypes: float64(1), int64(1), object(6)
memory usage: 37.2+ KB

women_per_100_men = women_per_100_men.drop(columns = ['DATAFLOW','LAST UPDATE', 'freq', 'indic_de', 'OBS_FLAG'])
women_per_100_men.head()

	geo	TIME_PERIOD	OBS_VALUE
0	AD	2010	92.0
1	AD	2011	96.0
2	AD	2012	96.0
3	AD	2013	96.3
4	AD	2019	96.4

old_age_dependency_ratio = pd.read_csv('F:\\STUDIA\\7SEM\\mit\\zad2\\dane\\old_age_dependency_ratio.csv')
old_age_dependency_ratio.head()

	DATAFLOW	LAST UPDATE	freq	indic_de	geo	TIME_PERIOD	OBS_VALUE	OBS_FLAG
0	ESTAT:TPS00198(1.0)	22/06/22 23:00:00	A	OLDDEP1	AD	2010	17.7	NaN
1	ESTAT:TPS00198(1.0)	22/06/22 23:00:00	A	OLDDEP1	AD	2011	17.6	NaN
2	ESTAT:TPS00198(1.0)	22/06/22 23:00:00	A	OLDDEP1	AD	2012	17.6	NaN
3	ESTAT:TPS00198(1.0)	22/06/22 23:00:00	A	OLDDEP1	AD	2013	17.5	NaN
4	ESTAT:TPS00198(1.0)	22/06/22 23:00:00	A	OLDDEP1	AD	2019	18.7	NaN

old_age_dependency_ratio = old_age_dependency_ratio.drop(columns = ['DATAFLOW','LAST UPDATE', 'freq', 'indic_de', 'OBS_FLAG'])
old_age_dependency_ratio.head()

	geo	TIME_PERIOD	OBS_VALUE
0	AD	2010	17.7
1	AD	2011	17.6
2	AD	2012	17.6
3	AD	2013	17.5
4	AD	2019	18.7

old_age_dependency_ratio.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 579 entries, 0 to 578
Data columns (total 3 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   geo          579 non-null    object 
 1   TIME_PERIOD  579 non-null    int64  
 2   OBS_VALUE    578 non-null    float64
dtypes: float64(1), int64(1), object(1)
memory usage: 13.7+ KB

proportion_of_population_aged_65_and_over = pd.read_csv('F:\\STUDIA\\7SEM\\mit\\zad2\\dane\\proportion_of_population_aged_65_and_over.csv')
proportion_of_population_aged_65_and_over.head()

	DATAFLOW	LAST UPDATE	freq	indic_de	geo	TIME_PERIOD	OBS_VALUE	OBS_FLAG
0	ESTAT:TPS00028(1.0)	22/06/22 23:00:00	A	PC_Y65_MAX	AD	2010	12.9	NaN
1	ESTAT:TPS00028(1.0)	22/06/22 23:00:00	A	PC_Y65_MAX	AD	2011	12.6	NaN
2	ESTAT:TPS00028(1.0)	22/06/22 23:00:00	A	PC_Y65_MAX	AD	2012	12.6	NaN
3	ESTAT:TPS00028(1.0)	22/06/22 23:00:00	A	PC_Y65_MAX	AD	2013	12.6	NaN
4	ESTAT:TPS00028(1.0)	22/06/22 23:00:00	A	PC_Y65_MAX	AD	2019	13.6	NaN

proportion_of_population_aged_65_and_over = proportion_of_population_aged_65_and_over.drop(columns = ['DATAFLOW','LAST UPDATE', 'freq', 'indic_de', 'OBS_FLAG'])
proportion_of_population_aged_65_and_over.head()

	geo	TIME_PERIOD	OBS_VALUE
0	AD	2010	12.9
1	AD	2011	12.6
2	AD	2012	12.6
3	AD	2013	12.6
4	AD	2019	13.6

proportion_of_population_aged_65_and_over.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 579 entries, 0 to 578
Data columns (total 3 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   geo          579 non-null    object 
 1   TIME_PERIOD  579 non-null    int64  
 2   OBS_VALUE    578 non-null    float64
dtypes: float64(1), int64(1), object(1)
memory usage: 13.7+ KB

population_by_age_group = pd.read_csv('F:\\STUDIA\\7SEM\\mit\\zad2\\dane\\population_by_age_group.csv')
population_by_age_group.head()

	DATAFLOW	LAST UPDATE	freq	indic_de	geo	TIME_PERIOD	OBS_VALUE	OBS_FLAG
0	ESTAT:TPS00010(1.0)	22/06/22 23:00:00	A	PC_Y0_14	AD	2010	14.5	NaN
1	ESTAT:TPS00010(1.0)	22/06/22 23:00:00	A	PC_Y0_14	AD	2011	15.5	NaN
2	ESTAT:TPS00010(1.0)	22/06/22 23:00:00	A	PC_Y0_14	AD	2012	15.5	NaN
3	ESTAT:TPS00010(1.0)	22/06/22 23:00:00	A	PC_Y0_14	AD	2013	15.5	NaN
4	ESTAT:TPS00010(1.0)	22/06/22 23:00:00	A	PC_Y0_14	AD	2019	13.9	NaN

population_by_age_group = population_by_age_group.drop(columns = ['DATAFLOW','LAST UPDATE', 'freq', 'OBS_FLAG'])
population_by_age_group.head()

	indic_de	geo	TIME_PERIOD	OBS_VALUE
0	PC_Y0_14	AD	2010	14.5
1	PC_Y0_14	AD	2011	15.5
2	PC_Y0_14	AD	2012	15.5
3	PC_Y0_14	AD	2013	15.5
4	PC_Y0_14	AD	2019	13.9

population_by_age_group.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3474 entries, 0 to 3473
Data columns (total 4 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   indic_de     3474 non-null   object 
 1   geo          3474 non-null   object 
 2   TIME_PERIOD  3474 non-null   int64  
 3   OBS_VALUE    3468 non-null   float64
dtypes: float64(1), int64(1), object(2)
memory usage: 108.7+ KB

population_change = pd.read_csv('F:\\STUDIA\\7SEM\\mit\\zad2\\dane\\population_change.csv')
population_change.head()

	DATAFLOW	LAST UPDATE	freq	indic_de	geo	TIME_PERIOD	OBS_VALUE	OBS_FLAG
0	ESTAT:TPS00019(1.0)	11/07/22 11:00:00	A	CNMIGRATRT	AD	2010	4.1	NaN
1	ESTAT:TPS00019(1.0)	11/07/22 11:00:00	A	CNMIGRATRT	AD	2012	-29.8	NaN
2	ESTAT:TPS00019(1.0)	11/07/22 11:00:00	A	CNMIGRATRT	AD	2016	14.5	e
3	ESTAT:TPS00019(1.0)	11/07/22 11:00:00	A	CNMIGRATRT	AD	2018	15.6	e
4	ESTAT:TPS00019(1.0)	11/07/22 11:00:00	A	CNMIGRATRT	AD	2019	14.7	e

population_change = population_change.drop(columns = ['DATAFLOW','LAST UPDATE', 'freq', 'OBS_FLAG'])
population_change.head()

	indic_de	geo	TIME_PERIOD	OBS_VALUE
0	CNMIGRATRT	AD	2010	4.1
1	CNMIGRATRT	AD	2012	-29.8
2	CNMIGRATRT	AD	2016	14.5
3	CNMIGRATRT	AD	2018	15.6
4	CNMIGRATRT	AD	2019	14.7

population_change.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1769 entries, 0 to 1768
Data columns (total 4 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   indic_de     1769 non-null   object 
 1   geo          1769 non-null   object 
 2   TIME_PERIOD  1769 non-null   int64  
 3   OBS_VALUE    1769 non-null   float64
dtypes: float64(1), int64(1), object(2)
memory usage: 55.4+ KB

population_as_percentage = pd.read_csv('F:\\STUDIA\\7SEM\\mit\\zad2\\dane\\population_as_percentage.csv')
population_as_percentage.head()

	DATAFLOW	LAST UPDATE	freq	indic_de	geo	TIME_PERIOD	OBS_VALUE	OBS_FLAG
0	ESTAT:TPS00005(1.0)	11/07/22 11:00:00	A	POPSHARE_EU27_2020	AT	2011	1.9	NaN
1	ESTAT:TPS00005(1.0)	11/07/22 11:00:00	A	POPSHARE_EU27_2020	AT	2012	1.9	NaN
2	ESTAT:TPS00005(1.0)	11/07/22 11:00:00	A	POPSHARE_EU27_2020	AT	2013	1.9	NaN
3	ESTAT:TPS00005(1.0)	11/07/22 11:00:00	A	POPSHARE_EU27_2020	AT	2014	1.9	NaN
4	ESTAT:TPS00005(1.0)	11/07/22 11:00:00	A	POPSHARE_EU27_2020	AT	2015	1.9	NaN

population_as_percentage = population_as_percentage.drop(columns = ['DATAFLOW','LAST UPDATE', 'freq', 'indic_de', 'OBS_FLAG'])
population_as_percentage.head()

	geo	TIME_PERIOD	OBS_VALUE
0	AT	2011	1.9
1	AT	2012	1.9
2	AT	2013	1.9
3	AT	2014	1.9
4	AT	2015	1.9

population_as_percentage.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 336 entries, 0 to 335
Data columns (total 3 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   geo          336 non-null    object 
 1   TIME_PERIOD  336 non-null    int64  
 2   OBS_VALUE    336 non-null    float64
dtypes: float64(1), int64(1), object(1)
memory usage: 8.0+ KB

population_as_percentage_PL = population_as_percentage[population_as_percentage['geo'] == 'PL']
population_as_percentage_DE = population_as_percentage[population_as_percentage['geo'] == 'DE']
population_as_percentage_FR = population_as_percentage[population_as_percentage['geo'] == 'FR']
population_as_percentage_HR = population_as_percentage[population_as_percentage['geo'] == 'HR']

fig1 = go.Figure()

fig1.add_trace(go.Bar(x = population_as_percentage_PL['TIME_PERIOD'], y = population_as_percentage_PL['OBS_VALUE'], marker_color = 'black', name = 'Polska (322 575 km^2)', opacity = 0.7))
fig1.add_trace(go.Bar(x = population_as_percentage_DE['TIME_PERIOD'], y = population_as_percentage_DE['OBS_VALUE'], marker_color = 'red', name = 'Niemcy (357 578 km^2)', opacity = 0.7))
fig1.add_trace(go.Bar(x = population_as_percentage_FR['TIME_PERIOD'], y = population_as_percentage_FR['OBS_VALUE'], marker_color = 'gold', name = 'Francja (543 940 km^2)', opacity = 0.7))
fig1.add_trace(go.Bar(x = population_as_percentage_HR['TIME_PERIOD'], y = population_as_percentage_HR['OBS_VALUE'], marker_color = 'blue', name = 'Węgry (93 025 km^2)', opacity = 0.7))

fig1.add_trace(go.Scatter(x = population_as_percentage_PL['TIME_PERIOD'], y = population_as_percentage_PL['OBS_VALUE'], mode = 'lines', marker_color = 'black',  name = 'Polska'))
fig1.add_trace(go.Scatter(x = population_as_percentage_DE['TIME_PERIOD'], y = population_as_percentage_DE['OBS_VALUE'], mode = 'lines', marker_color = 'red', name = 'Niemcy'))
fig1.add_trace(go.Scatter(x = population_as_percentage_FR['TIME_PERIOD'], y = population_as_percentage_FR['OBS_VALUE'], mode = 'lines', marker_color = 'gold', name = 'Francja'))
fig1.add_trace(go.Scatter(x = population_as_percentage_HR['TIME_PERIOD'], y = population_as_percentage_HR['OBS_VALUE'], mode = 'lines', marker_color = 'blue', name = 'Węgry'))

fig1.update_layout(title_text='Procentowa populacja krajów Unii europejskiej')
fig1.show()

population_by_age_group_PL = population_by_age_group[population_by_age_group['geo'] == 'PL']
population_by_age_group_DE = population_by_age_group[population_by_age_group['geo'] == 'DE']
population_by_age_group_FR = population_by_age_group[population_by_age_group['geo'] == 'FR']
population_by_age_group_HR = population_by_age_group[population_by_age_group['geo'] == 'HR']
population_by_age_group_EU28 = population_by_age_group[population_by_age_group['geo'] == 'EU28']

fig2 = go.Figure()

fig2.add_trace(go.Scatter3d(x = population_by_age_group_PL['TIME_PERIOD'], y = population_by_age_group_PL['indic_de'], z = population_by_age_group_PL['OBS_VALUE'], mode = 'markers', marker_color = 'black', name = 'Polska (322 575 km^2)'))
fig2.add_trace(go.Scatter3d(x = population_by_age_group_DE['TIME_PERIOD'], y = population_by_age_group_DE['indic_de'], z = population_by_age_group_DE['OBS_VALUE'], mode = 'markers', marker_color = 'red', name = 'Niemcy (357 578 km^2)'))
fig2.add_trace(go.Scatter3d(x = population_by_age_group_FR['TIME_PERIOD'], y = population_by_age_group_FR['indic_de'], z = population_by_age_group_FR['OBS_VALUE'], mode = 'markers', marker_color = 'gold', name = 'Francja (543 940 km^2)'))
fig2.add_trace(go.Scatter3d(x = population_by_age_group_HR['TIME_PERIOD'], y = population_by_age_group_HR['indic_de'], z = population_by_age_group_HR['OBS_VALUE'], mode = 'markers', marker_color = 'blue', name = 'Węgry (93 025 km^2)'))
fig2.add_trace(go.Scatter3d(x = population_by_age_group_EU28['TIME_PERIOD'], y = population_by_age_group_EU28['indic_de'], z = population_by_age_group_EU28['OBS_VALUE'], mode = 'markers', marker_color = 'pink', name = 'EU (28 krajów)'))

fig2.update_layout(autosize = False, width = 900, height = 1200)
fig2.update_layout(scene = dict(xaxis_title = '', yaxis_title = '', zaxis_title = ''))
fig2.update_layout(title = "Populacja według grup wiekowych")

fig2.show()

The crude rate of total change is the ratio of the population change during the year (the difference between the population sizes on 1 January of two consecutive years) to the average population in that year. The value is expressed per 1 000 persons. The crude rate of natural change is the ratio of the natural change during the year (live births minus deaths) to the average population in that year. The value is expressed per 1 000 persons. The crude rate of net migration plus adjustment is defined as the ratio of net migration (including statistical adjustment) during the year to the average population in that year. The value is expressed per 1000 persons. The net migration plus adjustment is calculated as the difference between the total change and the natural change of the population.

# CNMIGRATRT - Crude rate of net migration plus statistical adjustment (Wskaźnik salda migracji + korekta)
# GROWRT - Crude rate of total population change (Wskaźnik całkowitej zmiany populacji)
# NATGROWRT - Crude rate of natural change of population (Wskaźnik przyrostu naturalnego)

population_change_PL2 = population_change[population_change['geo'] == 'PL']
population_change_DE2 = population_change[population_change['geo'] == 'DE']

population_change_test = [dict(type = 'scatter3d', x = population_change_PL2['TIME_PERIOD'], y = population_change_PL2['indic_de'],z = population_change_PL2['OBS_VALUE'], mode = 'lines', name = "PL", transforms = [dict(type = 'groupby', groups = population_change_PL2['indic_de'],  styles = [
        dict(target = 'CNMIGRATRT', value = dict(marker = dict(color = 'black'))),
        dict(target = 'GROWRT', value = dict(marker = dict(color = 'black'))),
        dict(target = 'NATGROWRT', value = dict(marker = dict(color = 'black')))
    ])])]

population_change_test2 = [dict(type = 'scatter3d', x = population_change_DE2['TIME_PERIOD'], y = population_change_DE2['indic_de'],z = population_change_DE2['OBS_VALUE'], mode = 'lines', name = "DE", transforms = [dict(type = 'groupby', groups = population_change_DE2['indic_de'], styles = [
        dict(target = 'CNMIGRATRT', value = dict(marker = dict(color = 'red'))),
        dict(target = 'GROWRT', value = dict(marker = dict(color = 'red'))),
        dict(target = 'NATGROWRT', value = dict(marker = dict(color = 'red')))
    ])])]

popul = population_change_test + population_change_test2

fig_dict1 = dict(data = popul, scene = dict(xaxis_title = '', yaxis_title = '', zaxis_title = ''))

pio.show(fig_dict1, validate = False)